论文标题
在接受恐龙训练的视觉变压器中探索对抗性攻击和防御
Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINO
论文作者
论文摘要
这项工作是对对使用Dino训练的自制视觉变形金刚的对抗性攻击的鲁棒性进行的首次分析。首先，我们评估通过自学学会学到的特征是否比受到监督学习的人更强大。然后，我们介绍在潜在空间中攻击的属性。最后，我们评估了三种著名的防御策略是否仅通过微调分类头即使有限的计算资源即使可以提供鲁棒性来提高下游任务中的对抗性鲁棒性。这些防御策略是：对抗性训练，集合对抗训练和专业网络的合奏。
This work conducts the first analysis on the robustness against adversarial attacks on self-supervised Vision Transformers trained using DINO. First, we evaluate whether features learned through self-supervision are more robust to adversarial attacks than those emerging from supervised learning. Then, we present properties arising for attacks in the latent space. Finally, we evaluate whether three well-known defense strategies can increase adversarial robustness in downstream tasks by only fine-tuning the classification head to provide robustness even in view of limited compute resources. These defense strategies are: Adversarial Training, Ensemble Adversarial Training and Ensemble of Specialized Networks.
